Parse pdfbox versions and build a nice, robust representation

pdfbox_version_parsing.py

# SPDX-FileCopyrightText: 2023 geisserml <geisserml@gmail.com>
# SPDX-License-Identifier: CC-BY-4.0 OR Apache-2.0

import re
from datetime import datetime
from urllib.request import urlopen
from packaging.version import Version

PB_RELEASE_URL = "https://archive.apache.org/dist/pdfbox/"
PB_DISTS_RE = r'<a href="([\d\.]+.+?)/">.+</a>\s+([\d\-]+ [\d:]+)'
PB_DATE_FMT = r"%Y-%m-%d %H:%M"

content = urlopen(PB_RELEASE_URL).read().decode("utf-8")
results = [(Version(m.group(1)), datetime.strptime(m.group(2), PB_DATE_FMT)) for m in re.finditer(PB_DISTS_RE, content)]

ver_dict = {m: [] for m in {v.major for v, _ in results}}
for v, d in results:
    ver_dict[v.major].append( (v, d) )
for v in ver_dict.values():
    v.sort(key=lambda r: r[1])  # by date
for k, v in ver_dict.items():
    print(k, *v, sep="\n", end="\n\n")

latest_v3 = ver_dict[3][-1]
print(latest_v3)